检索结果-内蒙古大学图书馆

International Conference on Autonomous Agents and Multiagent Systems (AAMAS)

作者： Gomes, Jorge Inst Telecomunicacoes Lisbon Portugal Univ Lisbon Fac Ciencias LabMAg Lisbon Portugal

ISBN: (纸本)9781450327381

Heterogeneity is present in many collective systems found in nature and considered fundamental for effective task execution in several complex, real-world scenarios. evolutionary computation has the potential to automate the design of multirobot systems, but to date, it has mostly been applied to the design of homogeneous systems. We have recently demonstrated that novelty search can overcome deception and bootstrapping issues in the evolution of homogeneous robot swarms. In this research, we study how evolutionary techniques based on behavioural diversity (such as novelty search) can contribute to the evolution of heterogeneous multirobot systems. The results obtained so far show that novelty search can overcome open issues in the cooperative coevolution of multiagent systems, and lead to more effective and diverse solutions.

关键词： Coevolution behavioural diversity novelty search evolutionary robotics swarm robotics

来源：评论

学校读者我要写书评

暂无评论

Voxel Robot: A Pneumatic Robot with Deformable Morphology

Voxel Robot: A Pneumatic Robot with Deformable Morphology

引用

13th International Conference on the Simulation of Adaptive Behavior (SAB)

作者： Roper, Mark Katsaros, Nikolaos Fernando, Chrisantha Queen Mary Univ London SBCS EECS London England

ISBN: (纸本)9783319088648;9783319088631

The Voxbot is a cubic (voxel) shaped robot actuated by expansion and contraction of its 12 edges designed for running evolutionary experiments, built as cheaply as possible. Each edge was made of a single 10ml medical syringe for pneumatic control. These were connected to an array of 12 servos situated on an external housing and controlled with an Arduino microcontroller from a laptop. With twenty motor primitive commands and the slow response of its pneumatics this robot allows real time controllers to be evolved in situ rather than just in simulation. With simple combinations and sequencing of motor primitives the Voxbot can be made to walk, rotate and crab crawl. The device is available in kit form and is very easy to build and replicate. Other morphologies can be built easily.

关键词： Arduino Soft Bodied robotics evolutionary robotics Robustness

来源：评论

学校读者我要写书评

暂无评论

Evolving Joint-Level Control with Digital Muscles 14

Evolving Joint-Level Control with Digital Muscles

引用

16th Genetic and evolutionary Computation Conference (GECCO)

作者： Moore, Jared M. McKinley, Philip K. Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA

ISBN: (纸本)9781450326629

The neuromuscular systems of animals are governed by extremely complex networks of control signals, sensory feedback loops, and mechanical interactions. Morphology and control are inherently intertwined. In the case of animal joints, groups of muscles work together to provide power and stability to move limbs in a coordinated manner. In contrast, many robot controllers handle both high-level planning and low-level control of individual joints. In this paper, we propose a joint-level control method, called digital muscles, that operates in a manner analogous to biological muscles, yet is abstract enough to apply to conventional robotic joints. An individual joint is controlled by multiple muscle nodes, each of which responds to a control signal according to a node-specific activation function. Evolving the physical orientation of muscle nodes and their respective activation functions enables relatively complex and coordinated gaits to be realized with simple high-level control. Even using a sinusoid as the high-level control signal, we demonstrate the evolution of effective gaits for a simulated quadruped. The proposed model realizes a control strategy for governing the behavior of individual joints, and can be coupled with a high-level controller that focuses on decision making and planning.

关键词： evolutionary robotics digital muscles joint-level control simulation bio-inspired design

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Environments to Test the General Learning Capabilities of AI Agents 14

Automated Generation of Environments to Test the General Lea...

引用

16th Genetic and evolutionary Computation Conference (GECCO)

作者： Coleman, Oliver J. Blair, Alan D. Clune, Jeff Univ New S Wales Sch Comp Sci & Engn Sydney NSW 2052 Australia Univ Wyoming Dept Comp Sci Evolving AI Lab Laramie WY 82071 USA

ISBN: (纸本)9781450326629

Algorithms for evolving agents that learn during their lifetime have typically been evaluated on only a handful of environments. Designing such environments is labour intensive, potentially biased, and provides only a small sample size that may prevent accurate general conclusions from being drawn. In this paper we introduce a method for automatically generating MDP environments which allows the difficulty to be scaled in several ways. We present a case study in which environments are generated that vary along three key dimensions of difficulty: the number of environment configurations, the number of available actions, and the length of each trial. The study reveals interesting differences between three neural network models - Fixed-Weight, Plastic-Weight, and Modulated Plasticity - that would not have been obvious without sweeping across these different dimensions. Our paper thus introduces a new way of conducting reinforcement learning science: instead of manually designing a few environments, researchers will be able to automatically generate a range of environments across key dimensions of variation. This will allow scientists to more rigorously assess the general learning capabilities of an algorithm, and may ultimately improve the rate at which we discover how to create AI with general purpose learning.

关键词： Experimentation Algorithms evolutionary robotics Generative encodings Neural networks Learning Neuromodulation

来源：评论

学校读者我要写书评

暂无评论

Coupling Evolution and Information Theory for Autonomous Robotic Exploration

Coupling Evolution and Information Theory for Autonomous Rob...

引用

13th International Conference on Parallel Problem Solving from Nature (PPSN)

作者： Zhang, Guohua Sebag, Michele Chinese Acad Sci Chengdu Inst Comp Applicat Chengdu 610041 Peoples R China Univ Paris 11 CNRS INRIA LRI TAO F-91128 Orsay France

ISBN: (纸本)9783319107622;9783319107615

This paper investigates a hybrid two-phase approach toward exploratory behavior in robotics. In a first phase, controllers are evolved to maximize the quantity of information in the sensori-motor datastream generated by the robot. In a second phase, the data acquired by the evolved controllers is used to support an information theory-based controller, selecting the most informative action in each time step. The approach, referred to as EvITE, is shown to outperform both the evolutionary and the information theory-based approaches standalone, in terms of actual exploration of the arena. Further, the EvITE controller features some generality property, being able to efficiently explore other arenas than the one considered during the first evolutionary phase.

关键词： evolutionary robotics information theory intrinsic motivation entropy

来源：评论

学校读者我要写书评

暂无评论

Novelty Search in Competitive Coevolution

Novelty Search in Competitive Coevolution

引用

13th International Conference on Parallel Problem Solving from Nature (PPSN)

作者： Gomes, Jorge Mariano, Pedro Christensen, Anders Lyhne Inst Telecomunicacoes Lisbon Portugal Univ Lisbon Fac Ciencias LabMAg Lisbon Portugal Inst Univ Lisboa ISCTE IUL Lisbon Portugal

ISBN: (纸本)9783319107622;9783319107615

One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to sustain, and it has been shown that the competing species often converge prematurely to certain classes of behaviours. In this paper, we investigate if and how novelty search, an evolutionary technique driven by behavioural novelty, can overcome convergence in coevolution. We propose three methods for applying novelty search to coevolutionary systems with two species: (i) score both populations according to behavioural novelty;(ii) score one population according to novelty, and the other according to fitness;and (iii) score both populations with a combination of novelty and fitness. We evaluate the methods in a predator-prey pursuit task. Our results show that novelty-based approaches can evolve a significantly more diverse set of solutions, when compared to traditional fitness-based coevolution.

关键词： Competitive coevolution behavioural diversity novelty search convergence evolutionary robotics

来源：评论

学校读者我要写书评

暂无评论

Extending the evolutionary robotics approach to flying machines: An application to MAV teams

引用

NEURAL NETWORKS 2009年第5-6期22卷 812-821页

作者： Ruini, Fabio Cangelosi, Angelo Univ Plymouth Sch Comp & Math Ctr Robot & Neural Syst Adapt Behav & Cognit Res Grp Plymouth PL4 8AA Devon England

The work presented in this article focuses on the use of embodied neural networks - developed through evolutionary robotics and Multi-Agent Systems methodologies - as autonomous distributed controllers for Micro-unmanned Aerial Vehicle (MAV) teams. The main aim of the research is to extend the range of domains that could be successfully tackled by the evolutionary robotics approach. The flying robots realm is an area that has not been yet thoroughly investigated by this discipline. This is due to the lack of an affordable and reliable robotic platform to use for carrying out experiments, and to the difficulty and the high computational load involved in experiments based upon a realistic software simulator for aircraft. We believe that the most recent improvements to the state of the art now permit the investigation of this domain. For demonstrating this point, two different evolutionary computer simulation models are presented in this article. The first model, which uses a simplified 2D test environment, has resulted in controllers evolved with the following capabilities: (1) navigation through unknown environments, (2) obstacle-avoidance, (3) tracking of a movable target, and (4) execution of cooperative and coordinated behaviors based on implicit communication strategies. In order to improve the robustness of these results and their potential use in real MAV teams, a more sophisticated 3D model is presented herein. The results obtained so far using the two models demonstrate the feasibility of the chosen approach for further research on the design of autonomous controllers for MAVs. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： MAV Neural network Multi-Agent System evolutionary robotics Distributed control

来源：评论

学校读者我要写书评

暂无评论

In Vivo Veritas: Towards the Evolution of Things

In Vivo Veritas: Towards the Evolution of Things

引用

13th International Conference on Parallel Problem Solving from Nature (PPSN)

作者： Eiben, Agoston Endre Vrije Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9783319107622;9783319107615

The main thesis of the position paper is that in the near future it will be possible to create populations of animate physical objects that undergo evolution in real space and real time. The resulting systems will differ from evolutionary Computing in two crucial aspects. First, the individuals will be physical rather than digital. This requires reproduction operators for physical objects, which forms an engineering challenge. Second, the evolutionary process will be induced by the autonomous behavior of the individuals themselves, not by some central evolutionary agency that orchestrates selection and reproduction. These differences imply severe challenges for evolutionary algorithm designers because 'tricks' that work in in silico may not work in vivo. However, overcoming these challenges will ignite the development of a new field that combines evolutionary Computing, robotics, Artificial Life, and Embodied AI with a great potential for engineering as well as scientific research.

关键词： Embodied Evolution evolutionary Computing evolutionary robotics Self-reproducing Robots

来源：评论

学校读者我要写书评

暂无评论

Fitness functions in evolutionary robotics: A survey and analysis

引用

robotics AND AUTONOMOUS SYSTEMS 2009年第4期57卷 345-370页

作者： Nelson, Andrew L. Barlow, Gregory J. Doitsidis, Lefteris Androtics LLC Tucson AZ 85733 USA Carnegie Mellon Univ Inst Robot Pittsburgh PA 15213 USA Tech Univ Crete Dept Prod Engn & Management Intelligent Syst & Robot Lab Hania 73132 Greece

This paper Surveys Fitness functions used in the field of evolutionary robotics (ER). evolutionary robotics is a field of research that applies artificial evolution to generate control systems for autonomous robots. During evolution, robots attempt to perform a given task in a given environment. The controllers in the better performing robots are selected, altered and propagated to perform the task again in an iterative process that mimics some aspects of natural evolution. A key component of this process - one might argue, the key component - is the measurement of Fitness in the evolving controllers. ER is one of a host of machine learning methods that rely oil interaction with, and feedback from, a complex dynamic environment to drive synthesis of controllers for autonomous agents. These methods have the potential to lead to the development of robots that can adapt to uncharacterized environments and which may be able to perform tasks that human designers do not completely understand. In order to achieve this, issues regarding fitness evaluation must be addressed. In this paper we survey current ER research and focus oil work that involved real robots. The Surveyed research is organized according to the degree of a priori knowledge used to formulate the various Fitness functions employed during evolution. The underlying motivation for this is to identify methods that allow the development of the greatest degree of novel control, while requiring the minimum amount of a priori task knowledge from the designer. (c) 2008 Elsevier B.V. All rights reserved.

关键词： evolutionary robotics Fitness functions Genetic algorithms Autonomous learning robots Artificial life

来源：评论

学校读者我要写书评

暂无评论

The evolutionary Locomotion of Tripedal and Quadrupedal Biomorphic Robots

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2013年第4期29卷 681-693页

作者： Qiu, Guo-Yuan Wu, Shih-Hung Chaoyang Univ Technol Dept Comp Sci & Informat Engn Taichung 413 Taiwan

evolutionary robots can achieve certain goals via evolutionary algorithms without specifying all the detailed actions. The robot interacts with the environment and receives natural feedback as the fitness of its goal. In this paper, we study two biomorphic robots and observe how the behavior can evolve with least computation resources and test the possibility of self-adjustment on an unexpected motor failure of one robot leg. The feedback is collected via a supersonic sensor and the evolutionary algorithm is a modified low cost genetic algorithm. In order to minimize the cost of evolution, we control the number of the population of each generation to a very low number. We find that the biomorphic robots can move faster with the motion sequence generated by the evolutionary algorithm than with the motion sequence assigned by human programmers. The structures of robots, in this case, and the number of legs might affect the speed of convergence. Our experiment result shows that the robot can adjust itself with this online evolving approach to deal with an unexpected motor fault. That is, evolutionary robot can overcome an unexpected situation without human intervention.

关键词： evolutionary robotics biomorphic robot evolutionary algorithm adaptive robot tripedal robot

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：